Hispanic Legacy

com.hispanic-legacyv0.6.14Updated Sep 29, 2026

Spain's contributions to world science, exploration and culture, rigorously sourced

VerifiedStreamable HTTPWeb executableOther

Installation

In SourceWeft

  1. Open Hispanic Legacy in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "hispanic-legacy": {
      "type": "http",
      "url": "https://hispanic-legacy.com/mcp?via=manifest"
    }
  }
}

README

Hispanic Legacy — MCP server

Spain's contributions to world science, exploration and culture, rigorously sourced

[smithery badge]

A remote MCP server over a curated knowledge graph. Every claim it returns is bound to a registered source: the tools hand back claims with their citations and a confidence value, so an agent can show its work instead of asserting.

Nothing to install. It is a hosted streamable-HTTP endpoint:

https://hispanic-legacy.com/mcp

Also listed on Smithery.

Add it to a client

Claude Code

bash
claude mcp add --transport http hispanic-legacy https://hispanic-legacy.com/mcp

Claude Desktop / any client reading mcpServers

json
{  "mcpServers": {    "hispanic-legacy": {      "type": "streamable-http",      "url": "https://hispanic-legacy.com/mcp"    }  }}

No API key, no account, no auth. Read-only.

Check it answers, without any client at all:

bash
curl -s https://hispanic-legacy.com/mcp \  -H 'Content-Type: application/json' \  -H 'Accept: application/json, text/event-stream' \  -H 'mcp-protocol-version: 2025-06-18' \  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

Tools

Eight, each with an outputSchema, each returning structuredContent.

toolargumentswhat it does
get_overview—Corpus overview: what this instance knows, counts by type, published tags, freshness. Start here when you land and do not yet know whether this corpus can answer your question.
searchquery, limit?Full-text search over the knowledge graph. Accent- and apostrophe-insensitive, so query in the user's own words; every hit carries its relevance score and the fields it matched.
answerquestionAnswer a question from the corpus. Returns the matched object's claims with sources and confidence — never an unsourced answer.
get_entityidFetch one knowledge object by id, with its claims and the sources each claim cites.
get_topictagList the knowledge objects carrying a tag (topics are content-backed tags).
get_relatedidGraph neighbours of an object: outgoing and incoming relations, each with its relation type.
get_sourcesobject_id?The whole source registry, or just the sources cited by one object. Use it to judge the corpus before trusting it.
get_latestlimit?Most recently verified knowledge objects — a freshness signal.

The intended path is get_overview → search or answer → get_entity → get_related. get_overview exists because an agent that has just arrived needs to know whether this corpus can help before it spends a call guessing.

What is in the corpus

knowledge objects701
registered sources816
published topics534
typeobjects
entity681
comparison11
guide5
glossary3
faq1

Subject matter: the Balmis expedition and early public health, cartography and navigation, botany and the American expeditions, mining and metallurgy, universities and archives, and the historiography of the Black Legend — evidence, not polemic.

Questions it is built to answer

  • How was the smallpox vaccine actually carried across the Atlantic in 1803?
  • What did the Casa de Contratación do with the charts it collected?
  • Which claims about the Black Legend rest on primary sources, and which do not?

What an answer actually looks like

A real call against the live endpoint — answer with "how was the smallpox vaccine carried across the Atlantic" — returns this structuredContent, trimmed:

json
{  "answered": true,  "entity": {    "id": "keeping-the-vaccine-alive-in-spanish-america",    "name": "Keeping the vaccine alive: vaccine boards, conservators and human reservoirs in Spanish America, 1805-1815",    "evidence_tier": "secondary",    "confidence": 0.8,    "last_verified": "2026-08-12",    "canonical_url": "https://hispanic-legacy.com/k/keeping-the-vaccine-alive-in-spanish-america"  },  "claims": [    {      "text": "A colonial vaccine board published its own numbers, and they survive in print. The Semanario of Bogotá carried in 1808 a \"Noticia del número de personas que se han vacunado en esta capital…\"",      "sources": [{ "title": "Semanario de la Nueva Granada, publicada por una sociedad de patriotas Granadinos, bajo la dirección de Francisco José de Caldas" }]    }  ]}

Note what travels with the answer: the evidence tier, a confidence, the date it was last verified, and the source behind the claim — not as prose an agent has to parse, but as fields it can act on. An agent can decline to use a weak claim, or cite the primary source directly.

When the corpus cannot answer, answered is false. It does not improvise, and the miss is recorded so the gap can be filled.

Machine-readable surfaces

The MCP endpoint is one of several. The same corpus is served as plain files an agent can read directly:

surfacewhat it is
/llms.txtthe index, as text/plain
/llms-full.txtthe whole corpus in one file
/ai-index.jsonevery surface this instance publishes, with its content type
/api/index.jsonone JSON document per knowledge object
/api/sources.jsonthe source registry, in full
/.well-known/mcp/server.jsonthis server's manifest

Each knowledge object has a human page and a machine twin at the same id, with a canonical URL that agrees across all of them.

Behaviour worth knowing before you integrate

  • POST only. Every other method answers 405 with an Allow: POST, OPTIONS header.
  • Rate limit: 120 requests per minute per client, counted in a shared store, published on every response as RateLimit-Limit, RateLimit-Remaining and RateLimit-Reset (all three exposed via CORS). It fails open: if the store is unreachable the request is served.
  • Malformed input gets a spec-correct JSON-RPC error — -32700 for unparseable bodies, -32602 for an unknown tool — never an HTML error page.
  • Request bodies are capped and validated before transport.

Privacy

No accounts, no cookies, no ads. Usage is measured in aggregate with daily-rotating hashed identifiers and a 200-day retention; raw IPs are never stored. Full policy: PRIVACY.md.

Provenance and licence

Knowledge content is CC-BY-4.0: use it, cite it. The source registry is public precisely so a claim can be checked rather than trusted — get_sources returns what any given claim rests on.

Claims carry an evidence tier and a last_verified date. Where the evidence is weaker, the object says so rather than rounding up.

How it is built

Compiled and served by Citarium, a source-available framework for turning a knowledge graph into a website, an API, an MCP server and agent-readable files from a single source, under external evaluation.

The framework's code is licensed under the Business Source License 1.1 and its repository is not public. What is public — and what actually matters for trusting an answer — is this server, the corpus it serves, and the registered source behind every claim: get_sources returns what any given claim rests on, so it can be checked rather than trusted.

This repository is the server's public face: its manifest and its documentation. The corpus itself lives at hispanic-legacy.com.

Source: README.md at commit 21c347d

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v0.6.14LatestSep 16, 2026